Forcing Optimality and Brandt’s Principle

Napoletani, Domenico; Panza, Marco; Struppa, Daniele C.

doi:10.1007/978-3-319-54469-4_13

Cited by 3 publications

(22 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we showed in [13,16], boosting algorithms are a clear example of forcing. They are designed to improve weak classifiers, generally just slightly better than random ones, and to transform them, by iteration, in strong classifiers.…”

Section: Forcing Optimalitymentioning

confidence: 86%

“…This local search can be done, for example, by using the gradient descent method ([5], section 4.3), which does not guarantee that we will reach the desired minimum, or even a significant relative minimum. Since virtually all significant supervised machine learning methods can be shown to be equivalent to point by point optimization [16], we will briefly describe the gradient descent method.…”

Section: Forcing Optimalitymentioning

confidence: 99%

“…While we do not advance here any comprehensive reason for the effectiveness of data science, we observe that no account is possible unless we engage in a technical inquiry on how these algorithms work, and suggest a largely schematic account of their modus operandi. This account relies on the results of our previous works [13], [15], [16], which we reorganize in a comprehensive way. Furthermore, we identify a possible direction for future researches, and a promising perspective from which the question can be tackled.…”

Section: Introductionmentioning

confidence: 99%

“…In Section 4, we will go further in our analysis of agnostic science, by investigating the relations between optimization and "forcing", a term we first introduced in this context in [13]. More specifically, by forcing we referred in [16] to the following methodological practice:…”

Section: Introductionmentioning

confidence: 99%

“…Our suggestion is based on the observation that blind methods can be regarded as complying with a simple and general prescription for algorithms' development, what we called "Brandt's Principle" in [16]. We then discuss the way in which data science ( [7], Chapter 16) relies on entire families of methods ("ensemble methods"), and we interpret it in light of the Microarray Paradigm, ultimately showing how this forces some implicit analytic constraints on blind methods.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

The Agnostic Structure of Data Science Methods

Napoletani¹,

Panza²,

Struppa³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Section: Forcing Optimalitymentioning

confidence: 86%

Section: Forcing Optimalitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Agnostic Structure of Data Science Methods

Napoletani¹,

Panza²,

Struppa³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The Agnostic Structure of Data Science Methods

Napoletani¹,

Panza²,

Struppa³

2021

Lato Sensu

View full text Add to dashboard Cite

In this paper we argue that data science is a coherent and novel approach to empirical problems that, in its most general form, does not build understanding about phenomena. Within the new type of mathematization at work in data science, mathematical methods are not selected because of any relevance for a problem at hand; mathematical methods are applied to a specific problem only by `forcing’, i.e. on the basis of their ability to reorganize the data for further analysis and the intrinsic richness of their mathematical structure. In particular, we argue that deep learning neural networks are best understood within the context of forcing optimization methods. We finally explore the broader question of the appropriateness of data science methods in solving problems. We argue that this question should not be interpreted as a search for a correspondence between phenomena and specific solutions found by data science methods; rather, it is the internal structure of data science methods that is open to precise forms of understanding.

show abstract

The Challenges of Machine Learning: A Critical Review

Barbierato,

Gatti

2024

Electronics

View full text Add to dashboard Cite

The concept of learning has multiple interpretations, ranging from acquiring knowledge or skills to constructing meaning and social development. Machine Learning (ML) is considered a branch of Artificial Intelligence (AI) and develops algorithms that can learn from data and generalize their judgment to new observations by exploiting primarily statistical methods. The new millennium has seen the proliferation of Artificial Neural Networks (ANNs), a formalism able to reach extraordinary achievements in complex problems such as computer vision and natural language recognition. In particular, designers claim that this formalism has a strong resemblance to the way the biological neurons operate. This work argues that although ML has a mathematical/statistical foundation, it cannot be strictly regarded as a science, at least from a methodological perspective. The main reason is that ML algorithms have notable prediction power although they cannot necessarily provide a causal explanation about the achieved predictions. For example, an ANN could be trained on a large dataset of consumer financial information to predict creditworthiness. The model takes into account various factors like income, credit history, debt, spending patterns, and more. It then outputs a credit score or a decision on credit approval. However, the complex and multi-layered nature of the neural network makes it almost impossible to understand which specific factors or combinations of factors the model is using to arrive at its decision. This lack of transparency can be problematic, especially if the model denies credit and the applicant wants to know the specific reasons for the denial. The model’s “black box” nature means it cannot provide a clear explanation or breakdown of how it weighed the various factors in its decision-making process. Secondly, this work rejects the belief that a machine can simply learn from data, either in supervised or unsupervised mode, just by applying statistical methods. The process of learning is much more complex, as it requires the full comprehension of a learned ability or skill. In this sense, further ML advancements, such as reinforcement learning and imitation learning denote encouraging similarities to similar cognitive skills used in human learning.

show abstract

Forcing Optimality and Brandt’s Principle

Cited by 3 publications

References 35 publications

The Agnostic Structure of Data Science Methods

The Agnostic Structure of Data Science Methods

The Agnostic Structure of Data Science Methods

The Challenges of Machine Learning: A Critical Review

Contact Info

Product

Resources

About